Skip to main content
SpringerLink
Log in

Quasi-Deterministic Partially Observable Markov Decision Processes

  • Conference paper
Neural Information Processing (ICONIP 2009)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 5863))

Included in the following conference series:

Abstract

We study a subclass of pomdps, called quasi-deterministic pomdps (qDet- pomdps), characterized by deterministic actions and stochastic observations. While this framework does not model the same general problems as pomdps, they still capture a number of interesting and challenging problems and, in some cases, have interesting properties. By studying the observability available in this subclass, we show that qDet- pomdps may fall many steps in the complexity classes of polynomial hierarchy.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 129.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 169.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Nau, D., Ghallab, M., Traverso, P.: Automated Planning: Theory & Practice. Morgan Kaufmann Publishers Inc., San Francisco (2004)

    MATH  Google Scholar 

  2. Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and Acting in Partially Observable Stochastic Domains. Artif. Intell. 101(1-2), 99–134 (1998)

    Article  MATH  MathSciNet  Google Scholar 

  3. Palacios, H., Geffner, H.: From Conformant into Classical Planning: Efficient Translations that May Be Complete Too. In: Proc. of the 17th Int. Conf. on Automated Planning and Scheduling, pp. 264–271 (2007)

    Google Scholar 

  4. Amir, E., Chang, A.: Learning Partially Observable Deterministic Action Models. J. Artif. Intell. Res. 33, 349–402 (2008)

    MATH  MathSciNet  Google Scholar 

  5. Littman, M.: Algorithms for Sequential Decision Making. PhD thesis, Department of Computer Science, Brown University (1996)

    Google Scholar 

  6. Bonnet, B.: Deterministic POMDPs Revisited. In: Proc. of Uncertainty in Artificial Intelligence (2009)

    Google Scholar 

  7. Pattipati, K., Alexandridis, M.: Application of Heuristic Search and Info. Theo. to Sequential fault Diagnosis. IEEE Trans. on Syst., Man and Cyb. 20(4), 872–887 (1990)

    Article  MATH  Google Scholar 

  8. Ji, S., Parr, R., Carin, L.: Nonmyopic multiaspect sensing with partially observable markov decision processes. IEEE Transactions on Signal Processing 55(6), 2720–2730 (2007)

    Article  MathSciNet  Google Scholar 

  9. Goldman, R.P., Boddy, M.S.: Expressive planning and explicit knowledge. In: Proc. of the 3rd Inter. Conf. on Artif. Intel. Planning Systems, pp. 110–117 (1996)

    Google Scholar 

  10. Sondik, E.J.: The optimal control of Partially Observable Markov Processes. PhD thesis, Stanford University (1971)

    Google Scholar 

  11. Papadimitriou, C., Tsisiklis, J.: The Complexity of Markov Decision Processes. Math. Oper. Res. 12(3), 441–450 (1987)

    Article  MATH  MathSciNet  Google Scholar 

  12. Stockmeyer, L.J.: The Polynomial-Time Hierarchy. Theor. Comput. Sci. 3(1), 1–22 (1976)

    Article  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, Laval University, Quebec, Canada

    Camille Besse & Brahim Chaib-draa

Authors
  1. Camille Besse
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Brahim Chaib-draa
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Electronic Engineering, City University of Hong Kong, Hong Kong,  

    Chi Sing Leung

  2. School of Electrical Engineering and Computer Science, Kyungpook National University, 1370 Sankyuk-Dong, Puk-Gu, 702-701, Taegu, Korea

    Minho Lee

  3. School of Information Technology, King Mongkut’s University of Technology Thonburi, 126 Pracha-U-Thit Rd., Bangmod, Thungkru, 10140, Bangkok, Thailand

    Jonathan H. Chan

Rights and permissions

Reprints and permissions

Copyright information

© 2009 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Besse, C., Chaib-draa, B. (2009). Quasi-Deterministic Partially Observable Markov Decision Processes. In: Leung, C.S., Lee, M., Chan, J.H. (eds) Neural Information Processing. ICONIP 2009. Lecture Notes in Computer Science, vol 5863. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-10677-4_27

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-10677-4_27

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-10676-7

  • Online ISBN: 978-3-642-10677-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation